# zhu-xlab/GlobalBuildingAtlas

GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models

Repository: https://github.com/zhu-xlab/GlobalBuildingAtlas
Canonical: https://ross.abutalabs.com/products/globalbuildingatlas
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-06T08:38:20+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 23, longevity 62
- inputs: {"age_days": 873, "days_push": 58, "days_rel": 300, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2198, forks 211 (observed 2026-08-28T04:06:25.472405+00:00)

## What it is
GlobalBuildingAtlas is an open dataset providing global building polygons, height attributes, and LoD1 3D building models derived via machine learning. The data is split across HuggingFace and mediaTUM due to mixed ODbL and CC BY-NC 4.0 licensing of its components.

## Use cases
- download global building footprint polygons for urban analysis
- get LoD1 3D building models for city modeling
- estimate building heights worldwide for energy or flood studies
- visualize global 3D buildings in a web viewer
- combine building footprints with height maps in GIS
- analyze urban density and built environment at global scale

## When to choose
- you need worldwide building polygons or 3D models rather than a single city or country
- you can accept machine-learning-derived data with some errors
- your use case is compatible with ODbL and CC BY-NC 4.0 licenses

## When to avoid
- you need commercially licensed data (parts are CC BY-NC, non-commercial)
- you require survey-grade accuracy rather than ML-derived estimates
- you need a single consolidated download without handling split license parts

## Facets
- artifact type: dataset
- maturity: active
- function: geospatial, machine-learning, data-science
- domain: data-science, machine-learning
- platform: cross-platform
- tags: building-footprints, 3d-buildings, lod1, global-dataset, urban-mapping, height-maps, geo, open-data, geospatial, maps, web-server

## Member repositories
- zhu-xlab/GlobalBuildingAtlas (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:25.472405+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:47:09.390559+00:00, confidence not recorded.
  - readme: https://github.com/zhu-xlab/GlobalBuildingAtlas (fetched 2026-08-28T04:06:25.472405+00:00, sha 92169beeee9e)
- Data as of 2026-08-30T08:39:29.467469+00:00.